Cargando…

An Information-Theoretic Analysis of the Cost of Decentralization for Learning and Inference under Privacy Constraints

In vertical federated learning (FL), the features of a data sample are distributed across multiple agents. As such, inter-agent collaboration can be beneficial not only during the learning phase, as is the case for standard horizontal FL, but also during the inference phase. A fundamental theoretica...

Descripción completa

Detalles Bibliográficos
Autores principales: Jose, Sharu Theresa, Simeone, Osvaldo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9030603/
https://www.ncbi.nlm.nih.gov/pubmed/35455148
http://dx.doi.org/10.3390/e24040485